Lin Song

发表论文 24 篇 · 总被引 1726 次 · h-index 10

代表论文

• YOLO-World: Real-Time Open-Vocabulary Object Detection (2024 · Computer Vision and Pattern Recognition · 被引 1030)
• SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation (2024 · arXiv.org · 被引 350)
• UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition (2023 · Computer Vision and Pattern Recognition · 被引 334)
• Meta-Adapter: An Online Few-shot Learner for Vision-Language Model (2023 · Neural Information Processing Systems · 被引 64)
• MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO (2025 · Neural Information Processing Systems · 被引 33)
• Low-Rank Approximation for Sparse Attention in Multi-Modal LLMs (2024 · Computer Vision and Pattern Recognition · 被引 27)